Training in progress epoch 0

README.md

@@ -1,26 +1,10 @@
 ---
-base_model: Shiva26/marian-finetuned-iitb-en-to-hi
+base_model: Shiva26/marian-finetuned-iitb-en-to-hi-v2
 tags:
 - generated_from_keras_callback
-- english to hindi
-- english to hindi translation
-- robust
-- medium size model
-- tensorflow
-- translator
-- translation
 model-index:
 - name: Shiva26/marian-finetuned-iitb-en-to-hi-v2
   results: []
-datasets:
-- cfilt/iitb-english-hindi
-language:
-- hi
-- en
-metrics:
-- bleu
-- sacrebleu
-library_name: transformers
 ---
 
 <!-- This model card has been generated automatically according to the information Keras had access to. You should
@@ -28,13 +12,11 @@ probably proofread and complete it, then remove this comment. -->
 
 # Shiva26/marian-finetuned-iitb-en-to-hi-v2
 
-This model is a fine-tuned version of [Shiva26/marian-finetuned-iitb-en-to-hi](https://huggingface.co/Shiva26/marian-finetuned-iitb-en-to-hi) on an cfilt/iitb-english-hindi dataset.
+This model is a fine-tuned version of [Shiva26/marian-finetuned-iitb-en-to-hi-v2](https://huggingface.co/Shiva26/marian-finetuned-iitb-en-to-hi-v2) on an unknown dataset.
 It achieves the following results on the evaluation set:
-
-- sacrebleu Score: 16.33637186072388 (previously>1.59983786493238)
-- Train Loss: 2.0584
-- Validation Loss: 3.1803
-- Epoch: 2
+- Train Loss: 2.3815
+- Validation Loss: 3.1585
+- Epoch: 0
 
 ## Model description
 
@@ -53,16 +35,14 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 37500, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
+- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': 4686, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
 - training_precision: float32
 
 ### Training results
 
 | Train Loss | Validation Loss | Epoch |
 |:----------:|:---------------:|:-----:|
-| 2.9850     | 3.4368          | 0     |
-| 2.3187     | 3.2323          | 1     |
-| 2.0584     | 3.1803          | 2     |
+| 2.3815     | 3.1585          | 0     |
 
 
 ### Framework versions
@@ -70,4 +50,4 @@ The following hyperparameters were used during training:
 - Transformers 4.33.0
 - TensorFlow 2.12.0
 - Datasets 2.1.0
-- Tokenizers 0.13.3
+- Tokenizers 0.13.3

config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "Shiva26/marian-finetuned-iitb-en-to-hi",
+  "_name_or_path": "Shiva26/marian-finetuned-iitb-en-to-hi-v2",
   "activation_dropout": 0.0,
   "activation_function": "swish",
   "add_bias_logits": false,

tf_model.h5

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:37f2cbb587921c2c9a838e60d085f0fb10bb2f508a58b7255a672547ae57a8ed
+oid sha256:b973a244ad3a71241a97ff5cee21ce3586123066eee45eb62fe964cba2c1fe7d
 size 306059944